AI 中文总结
针对三维多人运动预测中流匹配的结构一致性与智能体交互问题，提出先验引导残差流匹配框架，含DCP、DCI机制和解耦关节-运动架构，在多数据集上实现最优预测精度。
AI 中文摘要
三维多人运动预测需要同时建模个体运动学和人际交互。流匹配（Flow Matching）能有效生成多假设以提升预测精度，但直接从纯噪声预测骨骼序列常会破坏结构一致性，并在早期噪声主导的积分步骤中引入不可靠的智能体间交互。为解决该问题，我们提出先验引导残差流匹配（Prior-Guided Residual Flow Matching）框架：首先，确定性粗先验（Deterministic Coarse Prior, DCP）建立运动学锚点，将生成过程建模为运动残差上的条件流，以简化生成目标并保持结构稳定性；其次，动态交叉交互（Dynamic Cross-Interaction, DCI）机制使智能体间消息传递与积分过程时间同步，确保提取可靠的社交上下文并提升多人运动保真度；最后，带双向融合的解耦关节-运动架构有效保留细粒度运动学连贯性。大量实验表明，我们的方法在多个数据集上实现了最优的预测精度，代码可在该 https URL 获取。
英文摘要
3D multi-person motion prediction requires modeling both individual kinematics and inter-person interactions. While Flow Matching is effective for multi-hypothesis generation to improve prediction accuracy, directly predicting skeletal sequences from pure noise often compromises structural consistency and introduces unreliable cross-agent interactions during early noise-dominated integration steps. To address this, we propose a Prior-Guided Residual Flow Matching framework. First, a Deterministic Coarse Prior (DCP) establishes a kinematic anchor, formulating the generative process as a conditional flow over motion residuals to simplify the generative objective and preserve structural stability. Second, a Dynamic Cross-Interaction (DCI) mechanism temporally synchronizes inter-agent message-passing with the integration progress, ensuring the extraction of reliable social contexts and improving multi-person motion fidelity. Finally, a decoupled joint-motion architecture with bidirectional fusion effectively preserves fine-grained kinematic coherence. Extensive experiments demonstrate that our approach achieves state-of-the-art prediction accuracy across multiple datasets. Code is available at https://github.com/Wei-Wei-a/Residual-Flow-Matching-with-Dynamic-Cross-Interaction-for-3D-Multi-Person-Motion-Prediction.
